CN113009452B - Laser point cloud power tower extraction method - Google Patents
Laser point cloud power tower extraction method Download PDFInfo
- Publication number
- CN113009452B CN113009452B CN201911326484.8A CN201911326484A CN113009452B CN 113009452 B CN113009452 B CN 113009452B CN 201911326484 A CN201911326484 A CN 201911326484A CN 113009452 B CN113009452 B CN 113009452B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- extraction
- point
- tower
- clouds
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 155
- 230000009466 transformation Effects 0.000 claims abstract description 46
- 238000012216 screening Methods 0.000 claims abstract description 12
- 238000007670 refining Methods 0.000 claims abstract description 5
- 238000000513 principal component analysis Methods 0.000 claims description 61
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000000034 method Methods 0.000 description 10
- 238000006243 chemical reaction Methods 0.000 description 7
- 238000007689 inspection Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention relates to a laser point cloud power tower extraction method, which comprises the following steps: acquiring an original point cloud, and setting an extraction range in the original point cloud; crude extraction: extracting point clouds with relative elevation values larger than a preset tower coarse extraction elevation threshold value in the extraction range as tower point clouds, and screening out point clouds which do not pass through coarse extraction; refining and extracting: and carrying out PCA transformation on the point clouds which are not subjected to the rough extraction, and extracting the tower point clouds according to the result of the PCA transformation. The extraction speed of the invention is far higher than that of manual extraction, the point cloud data can be extracted more accurately, the false extraction phenomenon caused by vegetation is avoided, and the precision is greatly improved.
Description
Technical Field
The invention relates to the field of power facility inspection, in particular to a laser point cloud power tower extraction method.
Background
Because the airborne laser radar system has higher positioning and ranging precision, the airborne laser radar system can be used for the operation and the maintenance of an electric overhead transmission line, such as: the method has the advantages of detecting dangerous ground objects in the line corridor, finely measuring the distance between the power lines, carrying out three-dimensional visual management on the power transmission line and the like, so that the laser point cloud is widely applied to line inspection. The power tower is used as an important asset for power inspection, and the extraction of the power tower in the power inspection process is an important step of the airborne laser radar inspection data processing.
At present, the method for extracting the point cloud of the pole tower mainly carries out manual extraction on the point cloud data by manpower, or directly takes all the point clouds in the space range of the pole tower as the point cloud of the pole tower, has low efficiency and extraction precision, and is easy to cause the situation of wrong extraction due to the existence of vegetation.
Disclosure of Invention
The invention aims at limiting the prior art, and provides a laser point cloud power tower extraction method which is realized by the following technical scheme:
a laser point cloud power tower extraction method comprises the following steps:
acquiring an original point cloud, and setting an extraction range in the original point cloud;
crude extraction: extracting point clouds with relative elevation values larger than a preset tower coarse extraction elevation threshold value in the extraction range as tower point clouds, and screening out point clouds which do not pass through coarse extraction, wherein the ground point clouds are extracted from the extraction range according to a preset ground fitting point elevation threshold value, a ground plane equation is obtained by carrying out ground plane fitting on the ground point clouds, point cloud coordinate parameters in the extraction range are input into the ground plane equation to obtain a ground fitting elevation, and the relative elevation value of the point clouds is obtained by the difference value of the actual elevation of the point clouds and the ground fitting elevation;
refining and extracting: performing PCA transformation on the point cloud which does not pass through the rough extraction, and extracting a tower point cloud according to the result of the PCA transformation, wherein the point cloud which does not pass through the rough extraction is subjected to the PCA transformation to obtain the characteristic value ratio of a first main component and a second main component of the point cloud which does not pass through the rough extraction after the PCA transformation, and the point cloud with the characteristic value ratio larger than a preset PCA transformation threshold value in the point cloud which does not pass through the rough extraction is used as the tower point cloud; or, performing block processing on the space where the point cloud which is not subjected to rough extraction is located according to the preset block size, screening out point cloud blocks with the point cloud from each block, performing PCA (principal component analysis) transformation on the point cloud in the point cloud blocks to obtain the characteristic value ratio of a first main component and a second main component of the point cloud after PCA transformation, and taking the point cloud in the point cloud block with the characteristic value ratio larger than a preset PCA transformation threshold value as a tower point cloud;
and (5) eliminating error points: clustering the pole tower point clouds obtained by refined extraction, and selecting the pole tower point clouds with the largest number of the point concentrated point clouds obtained by clustering as the pole tower point clouds after error points are removed.
Compared with the prior art, the extraction speed of the laser point cloud power tower extraction method is far higher than that of manual extraction, the point cloud data can be extracted more accurately, the false extraction phenomenon caused by vegetation is avoided, and the precision is improved greatly.
Further, clustering the refined extracted tower point cloud may include the following steps:
setting up a candidate library;
judging whether undetected point clouds in the refined extraction tower point clouds are clustered, if so, creating a new point set for the undetected point clouds to cluster, and storing the point clouds into the candidate library;
judging whether the candidate library is empty or not until all the tower point clouds obtained by the refined extraction are clustered, if not, taking out one point cloud from the candidate library, storing other point clouds which are not clustered in a neighborhood preset by the point cloud into the candidate library, and clustering the point clouds to a point set where the point cloud is located.
Further, the laser point cloud power tower extraction method may further include the following steps:
restoring the tower point cloud which is not extracted: and taking the tower point cloud with the error points removed as a center, and taking the point cloud existing in a given filter window range in the original point cloud as the tower point cloud.
Through the steps, the tower point cloud which is not extracted can be recovered.
A laser point cloud power tower extraction system, comprising:
the original point cloud extraction range setting module is used for acquiring an original point cloud and setting an extraction range in the original point cloud;
the tower point cloud rough extraction module is used for extracting point clouds with relative elevation values larger than a preset tower rough extraction elevation threshold value in the extraction range as tower point clouds, and screening out point clouds which do not pass through rough extraction, wherein ground point clouds are extracted from the extraction range according to a preset ground fitting point elevation threshold value, a ground plane equation is obtained by carrying out ground plane fitting on the ground point clouds, point cloud coordinate parameters in the extraction range are input into the ground plane equation to obtain a ground fitting elevation, and the relative elevation value of the point clouds is obtained by the difference value of the actual elevation of the point clouds and the ground fitting elevation;
the tower point cloud refining extraction module is used for carrying out PCA (principal component analysis) transformation on the point cloud which does not pass through the rough extraction, extracting tower point clouds according to the result of the PCA transformation, carrying out PCA transformation on the point cloud which does not pass through the rough extraction, obtaining the characteristic value ratio of a first main component and a second main component of the point cloud which does not pass through the rough extraction after the PCA transformation, and taking the point cloud with the characteristic value ratio larger than a preset PCA transformation threshold value in the point cloud which does not pass through the rough extraction as the tower point cloud; or, performing block processing on the space where the point cloud which is not subjected to rough extraction is located according to the preset block size, screening out point cloud blocks with the point cloud from each block, performing PCA (principal component analysis) transformation on the point cloud in the point cloud blocks to obtain the characteristic value ratio of a first main component and a second main component of the point cloud after PCA transformation, and taking the point cloud in the point cloud block with the characteristic value ratio larger than a preset PCA transformation threshold value as a tower point cloud;
and the tower point cloud error point eliminating module is used for clustering the tower point clouds obtained by the refined extraction, and selecting the tower point clouds with the maximum number of point concentrated point clouds obtained by the clustering as the tower point clouds after error points are eliminated.
The invention also provides a storage medium, on which a computer program is stored, which when being executed by a processor, implements the steps of the laser point cloud power tower extraction method.
The invention also provides a computer device which comprises a storage medium, a processor and a computer program stored in the storage medium and executable by the processor, wherein the computer program realizes the steps of the laser point cloud power tower extraction method when being executed by the processor.
For a better understanding and implementation, the present invention is described in detail below with reference to the drawings.
Drawings
FIG. 1 is a flowchart 1 of a method for extracting a laser point cloud power tower according to an embodiment of the present invention;
FIG. 2 is a flow chart of a crude extraction according to an embodiment of the present invention;
FIG. 3 is a flow chart of obtaining ground plane equations according to an embodiment of the present invention;
FIG. 4 is a flow chart 1 of a refinement of the present invention;
FIG. 5 is a flow chart of a refinement of the present invention 2;
FIG. 6 is a flowchart 2 of a method for extracting a laser point cloud power tower according to an embodiment of the present invention;
FIG. 7 is a flow chart of the method for eliminating error points according to the embodiment of the invention;
FIG. 8 is a flowchart 3 of a method for extracting a laser point cloud power tower according to an embodiment of the present invention;
FIG. 9 is a schematic diagram 1 of a laser point cloud power tower extraction system according to an embodiment of the present invention;
fig. 10 is a schematic diagram 2 of a laser point cloud power tower extraction system according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the following detailed description of the embodiments of the present application will be given with reference to the accompanying drawings.
It should be understood that the described embodiments are merely some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the embodiments of the present application, are within the scope of the embodiments of the present application.
The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of the application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims. In the description of this application, it should be understood that the terms "first," "second," "third," and the like are used merely to distinguish between similar objects and are not necessarily used to describe a particular order or sequence, nor should they be construed to indicate or imply relative importance. The specific meaning of the terms in this application will be understood by those of ordinary skill in the art as the case may be.
Furthermore, in the description of the present application, unless otherwise indicated, "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.
A laser point cloud power tower extraction method comprises the following steps:
s01, acquiring an original point cloud, and setting an extraction range in the original point cloud;
s02, crude extraction: extracting point clouds with relative elevation values larger than a preset tower coarse extraction elevation threshold value in the extraction range as tower point clouds, and screening out point clouds which do not pass through coarse extraction;
s03, fine extraction: and carrying out PCA transformation on the point clouds which are not subjected to the rough extraction, and extracting the tower point clouds according to the result of the PCA transformation.
Compared with the prior art, the extraction speed of the laser point cloud power tower extraction method is far higher than that of manual extraction, the point cloud data can be extracted more accurately, the false extraction phenomenon caused by vegetation is avoided, and the precision is improved greatly.
Specifically, the original point cloud refers to original data of the point cloud obtained by scanning the airborne laser radar in the power line inspection process.
The original point cloud comprises a patrol channel point cloud, so that the extraction range is set for reducing calculation and extracting a tower point cloud; the extraction range is the range of the tower area, the range completely comprises all tower point clouds, and the setting of the range comprises length and width, and the unit can be meters. The extraction range can be set directly, in an alternative embodiment, the center point coordinate of the target tower can be set first, and then the extraction range is set according to the center point coordinate of the target tower; in this way, the target tower can be quickly positioned in the original point cloud to improve the extraction efficiency of the tower point cloud, and in fact, as the extraction is carried out within the range in the extraction process, the setting of the coordinates of the central point of the target tower can allow certain deviation; the coordinates of the towers are positioned by the center point coordinates, so the coordinate system and the projection system of the center point coordinates should be consistent with those in the original point cloud.
Absolute elevation, i.e., altitude, refers to the distance of a ground point from the ground level in the direction of a vertical line; the relative elevation is the distance in the plumb line direction from a ground point assuming a level surface as the high Cheng Qisuan surface when the absolute elevation is not known in the local area.
Because the height of part of the electric power towers can reach nearly hundred meters, the preset tower rough extraction elevation threshold value is equivalent to dividing the space in which vegetation point clouds cannot exist, and the point clouds above the tower rough extraction elevation threshold value can be regarded as tower point clouds for extraction, so that the rough extraction of the tower point clouds is realized; the tower rough extraction elevation threshold set in this process is also a relative elevation value, which is an elevation relative to an assumed level or fitting plane.
PCA, principal component analysis (Principal components analysis), aims to find r (r < n) new variables, enable the new variables to reflect the main features of things, compress the scale of an original data matrix, reduce the dimension of feature vectors, and pick the least dimension to summarize the most important features. Each new variable is a linear combination of the original variables, the comprehensive effect of the original variables is reflected, and the new variables have certain practical meanings. These r new variables are called "principal components" which reflect to a large extent the effects of the original n variables and are uncorrelated with each other and also orthogonal. The data space is compressed by principal component analysis, and the characteristics of the multi-data are visually represented in a low-dimensional space. In this embodiment, the vegetation point clouds and the tower point clouds are mixed together, so that the vegetation point clouds are distributed more dispersedly, the tower point clouds are distributed more intensively, and the point clouds which are not subjected to coarse extraction are subjected to PCA conversion, so that the linear characteristics of the point clouds can be extracted, and the tower point clouds with more obvious linear characteristics than the vegetation point clouds are extracted from the vegetation point clouds.
Further, identifying the point cloud extraction with the relative elevation value greater than the preset tower coarse extraction elevation threshold value as the tower point cloud in the extraction range may include the following steps:
s021, extracting a ground point cloud from the extraction range according to a preset ground fitting point elevation threshold value, and obtaining a ground plane equation by carrying out ground plane fitting on the ground point cloud;
s022, inputting the point cloud coordinate parameters in the extraction range into the ground plane equation to obtain a ground fitting elevation, and obtaining a relative elevation value of the point cloud according to a difference value between the actual height of the point cloud and the ground fitting elevation.
Specifically, the point above the ground engaging point elevation threshold, i.e., the non-ground point, is also a relative elevation value, which is an average elevation relative to the point cloud in the extraction range, and therefore may be a negative value, and if a negative value, this indicates a lesser average elevation than the point cloud in the extraction range.
The step of obtaining a ground plane equation by performing ground plane fitting on the ground point cloud is as follows:
s021a, using the ground point cloud as a ground plane fitting input point, solving a fitting plane equation z=ax+by+c;
s021b, obtaining the distance from the ground plane fitting input point to the fitting plane, removing the point cloud higher than the preset fitting plane distance threshold value in the ground plane fitting input point to be used as update, re-solving the fitting plane equation according to the updated input point, and repeating the steps until the distance from the ground plane fitting input point to the fitting plane is smaller than the fitting plane distance threshold value and the corresponding fitting plane equation is used as the ground plane equation.
In an alternative embodiment, the fitted plane distance threshold is 3 meters.
In an alternative embodiment, PCA transformation is performed on the point cloud that is not subjected to the rough extraction, and the tower point cloud is extracted according to the result of PCA transformation, which may include the following steps:
s032a, performing PCA transformation on the point cloud which does not pass through the crude extraction to obtain the ratio of the characteristic values of the first main component and the second main component of the point cloud which does not pass through the crude extraction after the PCA transformation; and taking the point cloud, which is not subjected to rough extraction and has the characteristic value ratio larger than a preset PCA conversion threshold, as a tower point cloud.
Specifically, as vegetation point clouds are distributed more dispersedly, the information quantity difference between the first main component and the second main component after PCA transformation is not large; the distribution of the tower point clouds is concentrated, and the information difference between the first main component and the second main component after PCA conversion is large; therefore, the vegetation point cloud and the tower point cloud can be effectively distinguished by calculating the ratio of the characteristic values of the first main component and the second main component and comparing the ratio with the PCA conversion threshold value.
In another alternative embodiment, PCA transformation is performed on the point cloud that is not subjected to the rough extraction, and the tower point cloud is extracted according to the result of the PCA transformation, which may include the following steps:
s031b, performing block processing on the space where the point cloud which is not subjected to rough extraction is located according to the preset block size, and screening point cloud blocks with the point cloud from each block;
s032b, performing PCA transformation on the point clouds in the point cloud block to obtain the ratio of the characteristic values of the first main component and the second main component of the point clouds after PCA transformation; and taking the point cloud in the point cloud block with the characteristic value ratio larger than a preset PCA conversion threshold as the tower point cloud.
Specifically, the set block size refers to a value including length, width and height; the partitioning processing is to partition the point cloud which does not pass through the rough extraction in a three-dimensional space, remove the partitions which do not contain the point cloud, and respectively perform PCA (principal component analysis) transformation on each point cloud block which contains part of the point cloud which does not pass through the rough extraction, so that the extraction precision and efficiency can be further greatly improved.
Further, the laser point cloud power tower extraction method may further include the following steps:
s04, eliminating error points: clustering the pole tower point clouds obtained by refined extraction, and selecting the pole tower point clouds with the largest number of the point concentrated point clouds obtained by clustering as the pole tower point clouds after error points are removed.
Through the steps, the vegetation point cloud extracted by the object can be further removed.
Further, clustering the refined extracted tower point cloud may include the following steps:
s041, setting up a candidate library;
s042, judging whether undetected point clouds in the refined extraction tower point clouds are clustered, if so, creating a new point set for the undetected point clouds to cluster, and storing the point clouds into the candidate library;
s043, judging whether the candidate library is empty or not until all the tower point clouds obtained by the refined extraction are clustered, if not, taking out one point cloud from the candidate library, storing other point clouds which are not clustered in a neighborhood preset by the point cloud into the candidate library, and clustering the point clouds to a point set where the point clouds are located.
Further, the laser point cloud power tower extraction method may further include the following steps:
s05, recovering the tower point cloud which is not extracted: and taking the tower point cloud with the error points removed as a center, and taking the point cloud existing in a given filter window range in the original point cloud as the tower point cloud.
Through the steps, the tower point cloud which is not extracted can be recovered.
A laser point cloud power tower extraction system, comprising:
the original point cloud extraction range setting module 1 is used for acquiring an original point cloud and setting an extraction range in the original point cloud;
the tower point cloud rough extraction module 2 is used for extracting point clouds with relative elevation values larger than a preset tower rough extraction elevation threshold value in the extraction range as tower point clouds and screening point clouds which do not pass through rough extraction;
and the tower point cloud refined extraction module 3 is used for carrying out PCA conversion on the point clouds which do not pass through the rough extraction and extracting the tower point clouds according to the result of the PCA conversion.
Further, the laser point cloud power tower extraction system may further include:
and the error point eliminating module 4 is used for clustering the pole tower point clouds obtained by the refined extraction, and selecting the pole tower point clouds with the largest number of the point concentrated point clouds obtained by the clustering as the pole tower point clouds after error points are eliminated.
And the extracting-missing tower point cloud recovery module 5 is used for taking the tower point cloud with the error points removed as a center, and taking the point cloud existing in the given filtering window range in the original point cloud as the tower point cloud.
The present embodiment also provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the aforementioned laser point cloud power tower extraction method.
The embodiment also provides a computer device, which comprises a storage medium, a processor and a computer program stored in the storage medium and executable by the processor, wherein the computer program realizes the steps of the laser point cloud power tower extraction method when being executed by the processor.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention.
Claims (6)
1. The laser point cloud power tower extraction method is characterized by comprising the following steps of:
acquiring an original point cloud, and setting an extraction range in the original point cloud;
crude extraction: extracting point clouds with relative elevation values larger than a preset tower coarse extraction elevation threshold value in the extraction range as tower point clouds, and screening out point clouds which do not pass through coarse extraction, wherein the ground point clouds are extracted from the extraction range according to a preset ground fitting point elevation threshold value, a ground plane equation is obtained by carrying out ground plane fitting on the ground point clouds, point cloud coordinate parameters in the extraction range are input into the ground plane equation to obtain a ground fitting elevation, and the relative elevation value of the point clouds is obtained by the difference value of the actual elevation of the point clouds and the ground fitting elevation;
refining and extracting: performing PCA transformation on the point cloud which does not pass through the rough extraction, and extracting a tower point cloud according to the result of the PCA transformation, wherein the point cloud which does not pass through the rough extraction is subjected to the PCA transformation to obtain the characteristic value ratio of a first main component and a second main component of the point cloud which does not pass through the rough extraction after the PCA transformation, and the point cloud with the characteristic value ratio larger than a preset PCA transformation threshold value in the point cloud which does not pass through the rough extraction is used as the tower point cloud; or, performing block processing on the space where the point cloud which is not subjected to rough extraction is located according to the preset block size, screening out point cloud blocks with the point cloud from each block, performing PCA (principal component analysis) transformation on the point cloud in the point cloud blocks to obtain the characteristic value ratio of a first main component and a second main component of the point cloud after PCA transformation, and taking the point cloud in the point cloud block with the characteristic value ratio larger than a preset PCA transformation threshold value as a tower point cloud;
and (5) eliminating error points: clustering the pole tower point clouds obtained by refined extraction, and selecting the pole tower point clouds with the largest number of the point concentrated point clouds obtained by clustering as the pole tower point clouds after error points are removed.
2. The laser point cloud power tower extraction method according to claim 1, characterized in that clustering the tower point clouds obtained by the refined extraction comprises the steps of:
setting up a candidate library;
judging whether undetected point clouds in the refined extraction tower point clouds are clustered, if so, creating a new point set for the undetected point clouds to cluster, and storing the point clouds into the candidate library;
judging whether the candidate library is empty or not until all the tower point clouds obtained by the refined extraction are clustered, if not, taking out one point cloud from the candidate library, storing other point clouds which are not clustered in a neighborhood preset by the point cloud into the candidate library, and clustering the point clouds to a point set where the point cloud is located.
3. The laser point cloud power tower extraction method of claim 1, further comprising the steps of:
restoring the tower point cloud which is not extracted: and taking the tower point cloud with the error points removed as a center, and extracting the point cloud existing in a given filter window range from the original point cloud as the tower point cloud.
4. The utility model provides a laser point cloud electric power shaft tower draws system which characterized in that includes:
the original point cloud extraction range setting module is used for acquiring an original point cloud and setting an extraction range in the original point cloud;
the tower point cloud rough extraction module is used for extracting point clouds with relative elevation values larger than a preset tower rough extraction elevation threshold value in the extraction range as tower point clouds, and screening out point clouds which do not pass through rough extraction, wherein ground point clouds are extracted from the extraction range according to a preset ground fitting point elevation threshold value, a ground plane equation is obtained by carrying out ground plane fitting on the ground point clouds, point cloud coordinate parameters in the extraction range are input into the ground plane equation to obtain a ground fitting elevation, and the relative elevation value of the point clouds is obtained by the difference value of the actual elevation of the point clouds and the ground fitting elevation;
the tower point cloud refining extraction module is used for carrying out PCA (principal component analysis) transformation on the point cloud which does not pass through the rough extraction, extracting tower point clouds according to the result of the PCA transformation, carrying out PCA transformation on the point cloud which does not pass through the rough extraction, obtaining the characteristic value ratio of a first main component and a second main component of the point cloud which does not pass through the rough extraction after the PCA transformation, and taking the point cloud with the characteristic value ratio larger than a preset PCA transformation threshold value in the point cloud which does not pass through the rough extraction as the tower point cloud; or, performing block processing on the space where the point cloud which is not subjected to rough extraction is located according to the preset block size, screening out point cloud blocks with the point cloud from each block, performing PCA (principal component analysis) transformation on the point cloud in the point cloud blocks to obtain the characteristic value ratio of a first main component and a second main component of the point cloud after PCA transformation, and taking the point cloud in the point cloud block with the characteristic value ratio larger than a preset PCA transformation threshold value as a tower point cloud;
and the tower point cloud error point eliminating module is used for clustering the tower point clouds obtained by the refined extraction, and selecting the tower point clouds with the maximum number of point concentrated point clouds obtained by the clustering as the tower point clouds after error points are eliminated.
5. A storage medium having a computer program stored thereon, characterized by: the computer program, when executed by a processor, implements the steps of the laser point cloud power tower extraction method of any of claims 1 to 3.
6. A computer, characterized in that: comprising a storage medium, a processor, and a computer program stored in the storage medium and executable by the processor, which when executed by the processor, performs the steps of the laser point cloud power tower extraction method according to any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911326484.8A CN113009452B (en) | 2019-12-20 | 2019-12-20 | Laser point cloud power tower extraction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911326484.8A CN113009452B (en) | 2019-12-20 | 2019-12-20 | Laser point cloud power tower extraction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113009452A CN113009452A (en) | 2021-06-22 |
| CN113009452B true CN113009452B (en) | 2024-03-19 |
Family
ID=76382767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911326484.8A Active CN113009452B (en) | 2019-12-20 | 2019-12-20 | Laser point cloud power tower extraction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113009452B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116433750B (en) * | 2023-06-15 | 2023-08-18 | 国网江苏省电力有限公司苏州供电分公司 | Transmission tower extraction method and system based on laser point cloud |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701478A (en) * | 2016-02-24 | 2016-06-22 | 腾讯科技（深圳）有限公司 | Method and device for extraction of rod-shaped ground object |
| CN106897686A (en) * | 2017-02-19 | 2017-06-27 | 北京林业大学 | A kind of airborne LIDAR electric inspection process point cloud classifications method |
| CN107644452A (en) * | 2017-09-15 | 2018-01-30 | 武汉大学 | Airborne LiDAR point cloud roof dough sheet dividing method and system |
| CN108230336A (en) * | 2017-12-29 | 2018-06-29 | 国网通用航空有限公司 | A kind of cloud shaft tower extracting method and device |
| CN110570428A (en) * | 2019-08-09 | 2019-12-13 | 浙江合信地理信息技术有限公司 | method and system for segmenting roof surface patch of building from large-scale image dense matching point cloud |
-
2019
- 2019-12-20 CN CN201911326484.8A patent/CN113009452B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701478A (en) * | 2016-02-24 | 2016-06-22 | 腾讯科技（深圳）有限公司 | Method and device for extraction of rod-shaped ground object |
| CN106897686A (en) * | 2017-02-19 | 2017-06-27 | 北京林业大学 | A kind of airborne LIDAR electric inspection process point cloud classifications method |
| CN107644452A (en) * | 2017-09-15 | 2018-01-30 | 武汉大学 | Airborne LiDAR point cloud roof dough sheet dividing method and system |
| CN108230336A (en) * | 2017-12-29 | 2018-06-29 | 国网通用航空有限公司 | A kind of cloud shaft tower extracting method and device |
| CN110570428A (en) * | 2019-08-09 | 2019-12-13 | 浙江合信地理信息技术有限公司 | method and system for segmenting roof surface patch of building from large-scale image dense matching point cloud |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113009452A (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106709946B (en) | LiDAR point cloud-based automatic multi-split conductor extraction and fine modeling method | |
| CA2839165C (en) | Method and system for processing image data | |
| CN112883878B (en) | Automatic point cloud classification method under transformer substation scene based on three-dimensional grid | |
| CN111275821B (en) | Power line fitting method, system and terminal | |
| CN108562885B (en) | High-voltage transmission line airborne LiDAR point cloud extraction method | |
| CN110889828A (en) | Pallet identification method in predetermined scene, terminal device and computer storage medium | |
| CN110798805B (en) | Data processing method and device based on GPS track and storage medium | |
| CN113920134B (en) | Slope ground point cloud segmentation method and system based on multi-line laser radar | |
| CN113009452B (en) | Laser point cloud power tower extraction method | |
| CN114612616A (en) | Mapping method and device, electronic equipment and storage medium | |
| CN114187297A (en) | Power transmission line wind deflection checking method and checking system | |
| CN115825984A (en) | Power transmission line inspection system and inspection method based on laser point cloud | |
| CN116310849A (en) | Tree point cloud monomerization extraction method based on three-dimensional morphological characteristics | |
| CN117576325A (en) | Point cloud data processing method and device and point cloud data management system and method | |
| CN111783648A (en) | Method and device for extracting guardrail in road point cloud | |
| CN117197639A (en) | True value acquisition method and device, electronic equipment and storage medium | |
| CN111968253A (en) | Point cloud data-based road surface extraction method and system | |
| CN115143936B (en) | Method for measuring gradient of power transmission engineering pole tower based on laser point cloud | |
| CN112907574B (en) | Landing point searching method, device and system of aircraft and storage medium | |
| CN114610825A (en) | Method and device for confirming associated grid set, electronic equipment and storage medium | |
| CN112882047B (en) | Laser point cloud based automatic acquisition method and system for power line inter-phase distance | |
| CN107784682B (en) | Cable automatic extraction and reconstruction method based on three-dimensional point cloud data | |
| CN111507287A (en) | Method and system for extracting road zebra crossing corner points in aerial image | |
| CN110688919A (en) | Intelligent line patrol fault identification method | |
| CN116052003B (en) | Method and device for measuring antenna angle information and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |